The AI arena is free today

Open Superagent

LFM2.5-VL-3B vs MAI-Thinking-1

MAI-Thinking-1 significantly outperforms across most benchmarks.

Liquid AI · Microsoft · Updated for 2026

Which is better?

LFM2.5-VL-3B outperforms in 0 benchmarks, while MAI-Thinking-1 is better at 1 benchmark (IFBench). MAI-Thinking-1 significantly outperforms across most benchmarks.

Based on current benchmark, pricing, and model metadata for 2026.

Choose LFM2.5-VL-3B

  • you want the most recent training data — it shipped Aug 2026
  • you need open weights you can self-host or fine-tune

Choose MAI-Thinking-1

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks

At a glance

The differences that matter most.

LFM2.5-VL-3B
Liquid AI
MAI-Thinking-1
Microsoft
Benchmark wins
0 of 1
1 of 1
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—
Released
Aug 2026
Jun 2026
License
LFM Open License v1.0
Proprietary

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

LFM2.5-VL-3B outperforms in 0 benchmarks, while MAI-Thinking-1 is better at 1 benchmark (IFBench).

MAI-Thinking-1 significantly outperforms across most benchmarks.

Tue Aug 25 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

996.9B diff

MAI-Thinking-1 has 996.9B more parameters than LFM2.5-VL-3B, making it 31915.5% larger.

Liquid AI
LFM2.5-VL-3B
3.1Bparameters
Microsoft
MAI-Thinking-1
1.0Tparameters
3.1B
LFM2.5-VL-3B
1000.0B
MAI-Thinking-1

Input Capabilities

Supported data types and modalities

LFM2.5-VL-3B supports multimodal inputs, whereas MAI-Thinking-1 does not.

LFM2.5-VL-3B can handle both text and other forms of data like images, making it suitable for multimodal applications.

LFM2.5-VL-3B

Text
Images
Audio
Video

MAI-Thinking-1

Text
Images
Audio
Video

License

Usage and distribution terms

LFM2.5-VL-3B is licensed under LFM Open License v1.0, while MAI-Thinking-1 uses a proprietary license.

License differences may affect how you can use these models in commercial or open-source projects.

LFM2.5-VL-3B

LFM Open License v1.0

Open weights

MAI-Thinking-1

Proprietary

Closed source

Release Timeline

When each model was launched

LFM2.5-VL-3B was released on 2026-08-12, while MAI-Thinking-1 was released on 2026-06-02.

LFM2.5-VL-3B is 2 months newer than MAI-Thinking-1.

LFM2.5-VL-3B

Aug 12, 2026

1 weeks ago

2mo newer
MAI-Thinking-1

Jun 2, 2026

2 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against LFM2.5-VL-3B and MAI-Thinking-1 side-by-side, then vote on the output you prefer.

LFM2.5-VL-3B
✓ Preferred
MAI-Thinking-1
Open in Playground

FAQ

Common questions about LFM2.5-VL-3B vs MAI-Thinking-1.

Which is better, LFM2.5-VL-3B or MAI-Thinking-1?

MAI-Thinking-1 significantly outperforms across most benchmarks. LFM2.5-VL-3B is made by Liquid AI and MAI-Thinking-1 is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does LFM2.5-VL-3B compare to MAI-Thinking-1 in benchmarks?

LFM2.5-VL-3B scores DocVQA: 91.1%, POPE: 88.7%, RefCOCO-avg: 87.9%, TextVQA: 84.3%, OCRBench: 84.2%. MAI-Thinking-1 scores LongFact: 98.0%, AIME 2025: 97.0%, AIME 2026: 94.5%, GraphWalks: 90.0%, AIR-Bench: 88.0%.

What are the main differences between LFM2.5-VL-3B and MAI-Thinking-1?

Key differences include multimodal support (yes vs no), licensing (LFM Open License v1.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes LFM2.5-VL-3B and MAI-Thinking-1?

LFM2.5-VL-3B is developed by Liquid AI and MAI-Thinking-1 is developed by Microsoft.

Related comparisons